Update dependency @wllama/wllama to v2.3.0

[renovate]

This PR contains the following updates:

Package	Change	Age	Adoption	Passing	Confidence
@wllama/wllama	2.2.1 -> 2.3.0

---

Release Notes

ngxson/wllama (@​wllama/wllama)

v2.3.0

Compare Source

What's Changed

You can now use the stream: true option to get an AsyncIterator:

const messages: WllamaChatMessage[] = [
  { role: 'system', content: 'You are helpful.' },
  { role: 'user', content: 'Hi!' },
  { role: 'assistant', content: 'Hello!' },
  { role: 'user', content: 'How are you?' },
];
const stream = await wllama.createChatCompletion(messages, {
  nPredict: 10,
  sampling: {
    temp: 0.0,
  },
  stream: true, // ADD THIS
});

for await (const chunk of stream) {
  console.log(chunk.currentText);
}

---

Additionally, you can also use AbortSignal to stop a generation mid-way, much like how it's used in fetch API. Here is an example:

const abortController = new AbortController();
const stream = await wllama.createChatCompletion(messages, {
  abortSignal: abortController.signal, // ADD THIS
  stream: true,
});

// call abortController.abort(); to abort it
// note: this can also be called during prompt processing

---

Gemma 3 support: With the up-to-date llama.cpp source code, you can now use Gemma 3 models!

---

• build single-file mjs + minified version by @​ngxson in https://github.com/ngxson/wllama/pull/161
• bump to latest upstream llama.cpp source code by @​ngxson in https://github.com/ngxson/wllama/pull/162
• add support for async generator by @​ngxson in https://github.com/ngxson/wllama/pull/163
• add "stream" option for AsyncIterator by @​ngxson in https://github.com/ngxson/wllama/pull/164
• add test for abortSignal by @​ngxson in https://github.com/ngxson/wllama/pull/165
• bump to latest upstream llama.cpp source code by @​ngxson in https://github.com/ngxson/wllama/pull/166

Full Changelog: ngxson/wllama@2.2.1...2.3.0

---

Configuration

📅 Schedule: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined).

🚦 Automerge: Enabled.

♻ Rebasing: Whenever PR is behind base branch, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

---

• If you want to rebase/retry this PR, check this box

---

This PR was generated by Mend Renovate. View the repository job log.

[github-actions]

Review

The update from @wllama/wllama version 2.2.1 to 2.3.0 appears to be a straightforward version bump with no direct changes to the MiniSearch codebase. The release notes indicate new features such as streaming support and AbortSignal for chat completions, which could be beneficial but do not introduce any breaking changes or immediate issues.

Key Points:

• New Features: The new version includes streaming support and AbortSignal functionality, which could enhance the application's capabilities.
• Compatibility: The release notes suggest that the update is compatible with the previous version, as indicated by the passing compatibility badge.

Recommendations:

• Testing: Ensure that the new features do not introduce any regressions in existing functionality. Consider writing tests to verify the new streaming and abort functionalities.
• Documentation: Update any relevant documentation to reflect the new capabilities of @wllama/wllama.

Conclusion:

The PR can be merged if the new features do not cause any issues in the current implementation. No critical issues or security concerns were identified.

Approval: This PR can be merged once the new features are tested and documented.